Deterministic-first web extraction for AI, search & data pipelines. URL + schema -> validated JSON. LLM and browser only when needed.

1 stars 0 forks 1 watchers JavaScript Apache License 2.0
ai ai-agents crawler data-extraction data-pipeline etl json-ld llm nodejs playwright structured-data web-crawler web-data web-scraping
1 Open Issue Need Help Last updated: Aug 20, 2026

Open Issues Need Help

View All on GitHub
good first issue extraction-strategy

Deterministic-first web extraction for AI, search & data pipelines. URL + schema -> validated JSON. LLM and browser only when needed.

JavaScript
#ai#ai-agents#crawler#data-extraction#data-pipeline#etl#json-ld#llm#nodejs#playwright#structured-data#web-crawler#web-data#web-scraping